Comments (3)
When I use prior reservation, it tells me args.prior_loss_weight doesn't exist in the train_dreambooth.py line 796 loss = loss + args.prior_loss_weight * prior_loss
I quickly turned it into loss = loss + prior_loss just to test it and it seems to be churning well. I'm not sure where args.prior_loss_weight should be defined.
also it would be good to specify the labels correctly. db_train_batch_size = gr.Number(label="Batch Size", precision=1, value=1) db_sample_batch_size = gr.Number(label="Class Batch Size", precision=1, value=1) it's confusing, I needed to look into the code to see what is what. so Batch size should be labeled Train Batch Size etc...
This should have been fixed last night, at least the missing prior loss weight value.
As far as "confusing labels" go, I'll be writing up a readme for this today so it's not so esoteric. The problem with coming up with labels is that even the ones within the project don't necessarily line up with various terminology. For example, in one spot, the images used with Prior Preservation are referred as classifier images, but in other parts of the code, they're called "sample" images.
from sd_dreambooth_extension.
Thanks!
It successfully finished last night, but with the default and about steps 100x images, it brutally overtrained. I'm not sure where was the issue, I'll have to check. I'll try to do another batch today with the new pull.
Thanks, for making this - in general, it seems to be working well.
from sd_dreambooth_extension.
Thanks! It successfully finished last night, but with the default and about steps 100x images, it brutally overtrained. I'm not sure where was the issue, I'll have to check. I'll try to do another batch today with the new pull. Thanks, for making this - in general, it seems to be working well.
My pleasure.
Try ensuring you have a class prompt and around 100 for the class images as well, see if that helps with the overtraining.
Closing.
from sd_dreambooth_extension.
Related Issues (20)
- [Bug]: Can't create model using trained & generated model using dreambooth. HOT 3
- [Bug]: Exception training model: 'Cannot copy out of meta tensor; no data!'. HOT 2
- [Bug]: HOT 1
- [Bug]: The deprecation tuple ('LoRAAttnProcessor2_0', '0.26.0', 'Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`') should be removed since diffusers' version 0.26.1 is >= 0.26.0 HOT 4
- [Bug]: Completely unable to train any LORA with CUDA out of memory error HOT 2
- RuntimeError: Expected query, key, and value to have the same dtype, but got query.dtype: c10::Half key.dtype: float and value.dtype: float instead. HOT 9
- [Bug]: HOT 1
- [Bug]: OSError: Can't load tokenizer for 'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k'. HOT 2
- [Bug]: TypeError: intercept_args() got an unexpected keyword argument 'multiprocessing_context' HOT 1
- Error al cargar sd_dreambooth_extension en Windows 10: 'LoRAAttnProcessor2_0' no definido HOT 1
- [Bug]: Dreambooth (input tab) not showing correctly HOT 10
- [Bug]: Exception training model: 'type object 'LoraLoaderMixin' has no attribute '_modify_text_encoder''. HOT 4
- [Bug]: AttributeError: 'NoneType' object has no attribute 'unscale_grads' HOT 1
- [Bug]: Unable to further train using previously trained ckpt in dreambooth. HOT 1
- [Bug]: Dreambooth can not start training HOT 3
- AttributeError: module 'jax.random' has no attribute 'KeyArray'[Bug]: HOT 1
- [Bug]: Fast api of concepts don't work HOT 2
- [Bug]: AttributeError: 'NoneType' object has no attribute 'keys' HOT 1
- [Bug]: Unable to do training on sdxl model HOT 4
- [Bug]: Memory Attention default try to use xformers if Class Images Per Instance Image is greather that zero and need to generate images HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sd_dreambooth_extension.